Free to get · One-click to use
Creates and organizes focused planning views from a subset of roadmap tasks. Use when the user wants to build a task graph, analyze dependencies, identify ready or blocked work, or group near-term and future work into a focused planning workspace.
Claim and work on beads safely with proper coordination. Use when starting work, finishing work, or finding the next task. Covers the full bead lifecycle: discover → verify → claim → work → close.
Collaborative ideation for PM work — features, experiments, strategies, solutions. Use when doing creative work, exploring options, or turning a vague idea into a concrete plan.
Cross-session work orchestrator — view all active Claude Code sessions, todos, git status, and navigate between session details. Use when user wants a work overview, session management, task prioritization, or handoff notes. Trigger phrases include ccs, orchestrator, sessions overview, work dashboard, what am I working on.
Manages TODOs and long-horizon work using the bd (Beads) CLI: creates issues, links dependencies, finds ready work, and keeps the tracker synced via git and dolt. Use when tracking tasks across sessions, compaction, or multiple agents/branches. --- # Managing TODOs with Beads (bd) ## Quick start Prefer bd issues over ad-hoc markdown TODOs for any non-trivial workstream. 1) Ensure the repo is initialized: - Fresh clone / repair path: `bd bootstrap --dry-run --json`, then `bd bootstrap` - Human developer leading repo: `bd init --contributor --skip-hooks` - AI developer leading repo: `bd init --skip-hooks` - Human team collaboration repo workflow: `bd init --team --skip-hooks` - Legacy `.beads/issues.jsonl` repo: `bd init --from-jsonl --skip-hooks` 2) Load the live workflow context: `bd prime` 3) Find ready work with `bd ready --json`, and record new work with explicit context: `bd create "Short title" --description="Why this work exists" -t task -p 2 --json` 4) When you begin work on an issue, claim it atomically: `bd update <id> --claim --json` ## Default workflow - Start: `bd prime`, then `bd ready --json`; inspect with `bd show <id> --json` when needed. - Claim work with `bd update <id> --claim --json` instead of manually setting status flags. - During work: file discovered TODOs immediately as issues (bugs/tasks/features), include `--description`, and link provenance with `--deps discovered-from:<current-id>`. - Update issues non-interactively with `bd update` flags or `bd comments add`; do not rely on `bd edit` from an agent session. - End of session: close completed issues with `bd close <id> --reason "..." --json` (or `bd done <id> --reason "..." --json`), leave partial work open with fresh notes/next steps, and sync via Dolt (`bd dolt push` / `bd dolt pull`) or current hooks. If you initialized with `--skip-hooks`, install them later with `bd hooks install` when you want hook-managed sync/context injection. ## Reference - Commands: see [COMMANDS.md](COMMANDS.m
Work with Jira via the ACLI. Covers viewing, searching, creating, editing, transitioning, assigning, and commenting on tickets using acli jira subcommands. Use when the user wants to read or manage Jira work items from the terminal.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
